commit d28f0f2d0d6fc1fd6c2c706271b3ae9709796133 Author: ModelHub XC Date: Sat Oct 3 23:15:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..765c66d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-1.5B.i1-IQ1_M.gguf b/Qwen2.5-Coder-1.5B.i1-IQ1_M.gguf new file mode 100644 index 0000000..a976a82 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcb1fa44d8ebaf7b53a03768c1086a777485c8e94ff80474375ec9ab71be3c5 +size 464461984 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ1_S.gguf b/Qwen2.5-Coder-1.5B.i1-IQ1_S.gguf new file mode 100644 index 0000000..81774c2 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b826b4df160b1922e520866c8a4e852dd9c987f21cf1c3f4e4f821582146595 +size 436528288 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ2_M.gguf b/Qwen2.5-Coder-1.5B.i1-IQ2_M.gguf new file mode 100644 index 0000000..822f048 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc0f75ecc30a314057150ac6eefb4202edfc711ae112a7c8de973ed7c02bfa2 +size 601055392 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ2_S.gguf b/Qwen2.5-Coder-1.5B.i1-IQ2_S.gguf new file mode 100644 index 0000000..6750e17 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541cd91ffe7b02c2598b80a18806fa81488aaa85cdef160fbacc532884caa3d8 +size 563810464 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ2_XS.gguf b/Qwen2.5-Coder-1.5B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..971a1df --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74cfcecc70474e84890136382832808e02e0619b3289167a8747871e78b4fade +size 550327456 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ2_XXS.gguf b/Qwen2.5-Coder-1.5B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..60b02e6 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9390a5e72bed2983afe8e6a8ae1ef5b8167282d30226947912eb82437e8df08d +size 511018144 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ3_M.gguf b/Qwen2.5-Coder-1.5B.i1-IQ3_M.gguf new file mode 100644 index 0000000..769cc26 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea9eddb527cef6d91b0706bf8f1d778334d3325dfbda98e1b42b894f5d4a65c +size 776664736 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ3_S.gguf b/Qwen2.5-Coder-1.5B.i1-IQ3_S.gguf new file mode 100644 index 0000000..03c4128 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0e89ca65f734d386d677f8ac92aa1a962fd6bfedab0a0fffaf394cab00958c +size 762407584 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ3_XS.gguf b/Qwen2.5-Coder-1.5B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0ddc1ae --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3489ed7d79f52525f451f07ec533f3da8ee599338204170293df8d23e55682 +size 731699872 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ3_XXS.gguf b/Qwen2.5-Coder-1.5B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..40913d7 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83cc04366beb31feac910d7385be0d9d68b433723535fcd6fd9259c77c39ca0e +size 668792992 diff --git a/Qwen2.5-Coder-1.5B.i1-IQ4_XS.gguf b/Qwen2.5-Coder-1.5B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9152f72 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f98f41e043e009128de6fb99f7c9b1322ce8dcae26fe460666ddf3924c1297 +size 895732384 diff --git a/Qwen2.5-Coder-1.5B.i1-Q2_K.gguf b/Qwen2.5-Coder-1.5B.i1-Q2_K.gguf new file mode 100644 index 0000000..91392a4 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47dd9b9301b098ee28e8709a72bb987493f22fb369c1778a974fd4a0a06bcda +size 676305568 diff --git a/Qwen2.5-Coder-1.5B.i1-Q3_K_L.gguf b/Qwen2.5-Coder-1.5B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7efd5a3 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e123391177ea0ed8a06471bf22babeccc9359eccf20be9cd89d7fcb7465923 +size 880163488 diff --git a/Qwen2.5-Coder-1.5B.i1-Q3_K_M.gguf b/Qwen2.5-Coder-1.5B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6112720 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b268684b9fe1f12cca29e12735464d243f0856e170ae948c1d80da6a91c0ce1f +size 824179360 diff --git a/Qwen2.5-Coder-1.5B.i1-Q3_K_S.gguf b/Qwen2.5-Coder-1.5B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..226d121 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cec4607bc1d129f59c83aa4a2cb950787f259fa4469a0aaa328502ca7a65de +size 760945312 diff --git a/Qwen2.5-Coder-1.5B.i1-Q4_0.gguf b/Qwen2.5-Coder-1.5B.i1-Q4_0.gguf new file mode 100644 index 0000000..3c39fb2 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b59a422b6d8d242dc7f6ffe1120967707b779049430177ab9897eb51c7ac724 +size 937536160 diff --git a/Qwen2.5-Coder-1.5B.i1-Q4_0_4_4.gguf b/Qwen2.5-Coder-1.5B.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..6c0f955 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44ac740e4546cbfb1fefce724370a51324de1d054f633c145075cd2501c169db +size 934955680 diff --git a/Qwen2.5-Coder-1.5B.i1-Q4_0_4_8.gguf b/Qwen2.5-Coder-1.5B.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..6f0b3b2 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2965e7ce228c35004e2d88053d2ea2995adb1a5bbed680a86b2fdbf18612137 +size 934955680 diff --git a/Qwen2.5-Coder-1.5B.i1-Q4_0_8_8.gguf b/Qwen2.5-Coder-1.5B.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..864c99e --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc0934eb71bde366f9f4cff4cfef76b5cbc3731c273081c64956d05d074476f +size 934955680 diff --git a/Qwen2.5-Coder-1.5B.i1-Q4_K_M.gguf b/Qwen2.5-Coder-1.5B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f07a8a6 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5e4bad9cb8f2c58e64ebd86b49627bc6bd5afbe3e116211fda4b40b1b6469a +size 986049184 diff --git a/Qwen2.5-Coder-1.5B.i1-Q4_K_S.gguf b/Qwen2.5-Coder-1.5B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..dec730d --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8ace52aeb6972258e68ad5a27ee0191317c56f169bfd4501391285a26ed264 +size 940313248 diff --git a/Qwen2.5-Coder-1.5B.i1-Q5_K_M.gguf b/Qwen2.5-Coder-1.5B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7602642 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44154cdf16eb1bfe9c599378252b40d4a1371fe92af1ef489a0b463b13d213e0 +size 1125051040 diff --git a/Qwen2.5-Coder-1.5B.i1-Q5_K_S.gguf b/Qwen2.5-Coder-1.5B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..84e2859 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2d9a281972ea37a5dc651f185d18f719fe5f51112cd3a4654cdde77b1a6dba +size 1098730144 diff --git a/Qwen2.5-Coder-1.5B.i1-Q6_K.gguf b/Qwen2.5-Coder-1.5B.i1-Q6_K.gguf new file mode 100644 index 0000000..04dbea2 --- /dev/null +++ b/Qwen2.5-Coder-1.5B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f847cfb407ed673df2a4d0a9da100ee65a78a58081872072ee4fbcdae7ae04 +size 1272740512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5427dd6 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Qwen/Qwen2.5-Coder-1.5B +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B/blob/main/LICENSE +quantized_by: mradermacher +tags: +- code +- qwen +- qwen-coder +- codeqwen +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.0 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.0 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..da4ed47 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392aee4aeadb9071c51a890f0395d6552dc24344399cafb89c077ccd60ff8cfc +size 2042201